mizzaay commited on
Commit
7a69b87
·
verified ·
1 Parent(s): 2f2c1ce

Run 5. Outer Step 13. Inner Step 1.

Browse files
Files changed (3) hide show
  1. config.json +60 -60
  2. inner_optimizer.pt +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "mizzaay/l3",
3
  "all_reduce_scores": {
4
  "0": "NON_PARTICIPATING",
5
  "1": "NON_PARTICIPATING",
@@ -8,13 +8,13 @@
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
- "104": "NON_PARTICIPATING",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
- "11": "SUCCESS",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
@@ -41,24 +41,24 @@
41
  "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
43
  "133": "NON_PARTICIPATING",
44
- "134": "SUCCESS",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
- "14": "SUCCESS",
51
  "140": "NON_PARTICIPATING",
52
  "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
- "145": "NON_PARTICIPATING",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
- "15": "SUCCESS",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
@@ -80,7 +80,7 @@
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
- "17": "SUCCESS",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
@@ -91,7 +91,7 @@
91
  "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
- "18": "NON_PARTICIPATING",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
@@ -102,10 +102,10 @@
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
- "19": "NON_PARTICIPATING",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
- "192": "SUCCESS",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
@@ -113,8 +113,8 @@
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
- "2": "SUCCESS",
117
- "20": "SUCCESS",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
@@ -123,11 +123,11 @@
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
- "208": "SUCCESS",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
- "211": "SUCCESS",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
@@ -136,23 +136,23 @@
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
- "22": "SUCCESS",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
- "226": "SUCCESS",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
- "23": "SUCCESS",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
- "234": "NON_PARTICIPATING",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
@@ -179,84 +179,84 @@
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
- "29": "SUCCESS",
183
- "3": "NON_PARTICIPATING",
184
- "30": "SUCCESS",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
  "34": "SUCCESS",
189
- "35": "SUCCESS",
190
  "36": "NON_PARTICIPATING",
191
  "37": "SUCCESS",
192
- "38": "SUCCESS",
193
- "39": "SUCCESS",
194
  "4": "SUCCESS",
195
- "40": "SUCCESS",
196
- "41": "SUCCESS",
197
- "42": "SUCCESS",
198
  "43": "NON_PARTICIPATING",
199
- "44": "SUCCESS",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
- "49": "SUCCESS",
205
- "5": "NON_PARTICIPATING",
206
- "50": "NON_PARTICIPATING",
207
- "51": "NON_PARTICIPATING",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
- "54": "SUCCESS",
211
- "55": "NON_PARTICIPATING",
212
- "56": "SUCCESS",
213
- "57": "SUCCESS",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
- "6": "NON_PARTICIPATING",
217
- "60": "NON_PARTICIPATING",
218
- "61": "NON_PARTICIPATING",
219
  "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
- "66": "NON_PARTICIPATING",
224
  "67": "SUCCESS",
225
- "68": "SUCCESS",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "SUCCESS",
229
- "71": "SUCCESS",
230
- "72": "SUCCESS",
231
  "73": "NON_PARTICIPATING",
232
- "74": "NON_PARTICIPATING",
233
- "75": "NON_PARTICIPATING",
234
  "76": "NON_PARTICIPATING",
235
- "77": "SUCCESS",
236
  "78": "SUCCESS",
237
  "79": "SUCCESS",
238
- "8": "NON_PARTICIPATING",
239
  "80": "SUCCESS",
240
  "81": "NON_PARTICIPATING",
241
- "82": "SUCCESS",
242
  "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
245
- "86": "NON_PARTICIPATING",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NON_PARTICIPATING",
251
- "91": "SUCCESS",
252
  "92": "NON_PARTICIPATING",
253
- "93": "NON_PARTICIPATING",
254
  "94": "NON_PARTICIPATING",
255
- "95": "SUCCESS",
256
  "96": "NON_PARTICIPATING",
257
- "97": "SUCCESS",
258
- "98": "NON_PARTICIPATING",
259
- "99": "SUCCESS"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
@@ -264,17 +264,17 @@
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
- 5716395,
268
- 5716413
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
- "inner_step": 53,
276
  "intermediate_size": 5632,
277
- "last_allreduce_block": 5713917,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
 
1
  {
2
+ "_name_or_path": "distributed/llama-1b",
3
  "all_reduce_scores": {
4
  "0": "NON_PARTICIPATING",
5
  "1": "NON_PARTICIPATING",
 
8
  "101": "NON_PARTICIPATING",
9
  "102": "NON_PARTICIPATING",
10
  "103": "NON_PARTICIPATING",
11
+ "104": "SUCCESS",
12
  "105": "NON_PARTICIPATING",
13
  "106": "NON_PARTICIPATING",
14
  "107": "NON_PARTICIPATING",
15
  "108": "NON_PARTICIPATING",
16
  "109": "NON_PARTICIPATING",
17
+ "11": "NON_PARTICIPATING",
18
  "110": "NON_PARTICIPATING",
19
  "111": "NON_PARTICIPATING",
20
  "112": "NON_PARTICIPATING",
 
41
  "131": "NON_PARTICIPATING",
42
  "132": "NON_PARTICIPATING",
43
  "133": "NON_PARTICIPATING",
44
+ "134": "NON_PARTICIPATING",
45
  "135": "NON_PARTICIPATING",
46
  "136": "NON_PARTICIPATING",
47
  "137": "NON_PARTICIPATING",
48
  "138": "NON_PARTICIPATING",
49
  "139": "NON_PARTICIPATING",
50
+ "14": "NON_PARTICIPATING",
51
  "140": "NON_PARTICIPATING",
52
  "141": "SUCCESS",
53
  "142": "NON_PARTICIPATING",
54
  "143": "NON_PARTICIPATING",
55
  "144": "NON_PARTICIPATING",
56
+ "145": "SUCCESS",
57
  "146": "NON_PARTICIPATING",
58
  "147": "NON_PARTICIPATING",
59
  "148": "NON_PARTICIPATING",
60
  "149": "NON_PARTICIPATING",
61
+ "15": "NON_PARTICIPATING",
62
  "150": "NON_PARTICIPATING",
63
  "151": "NON_PARTICIPATING",
64
  "152": "NON_PARTICIPATING",
 
80
  "167": "NON_PARTICIPATING",
81
  "168": "NON_PARTICIPATING",
82
  "169": "NON_PARTICIPATING",
83
+ "17": "NON_PARTICIPATING",
84
  "170": "NON_PARTICIPATING",
85
  "171": "NON_PARTICIPATING",
86
  "172": "NON_PARTICIPATING",
 
91
  "177": "NON_PARTICIPATING",
92
  "178": "NON_PARTICIPATING",
93
  "179": "NON_PARTICIPATING",
94
+ "18": "SUCCESS",
95
  "180": "NON_PARTICIPATING",
96
  "181": "NON_PARTICIPATING",
97
  "182": "NON_PARTICIPATING",
 
102
  "187": "NON_PARTICIPATING",
103
  "188": "NON_PARTICIPATING",
104
  "189": "NON_PARTICIPATING",
105
+ "19": "SUCCESS",
106
  "190": "NON_PARTICIPATING",
107
  "191": "NON_PARTICIPATING",
108
+ "192": "NON_PARTICIPATING",
109
  "193": "NON_PARTICIPATING",
110
  "194": "NON_PARTICIPATING",
111
  "195": "NON_PARTICIPATING",
 
113
  "197": "NON_PARTICIPATING",
114
  "198": "NON_PARTICIPATING",
115
  "199": "NON_PARTICIPATING",
116
+ "2": "NON_PARTICIPATING",
117
+ "20": "NON_PARTICIPATING",
118
  "200": "NON_PARTICIPATING",
119
  "201": "NON_PARTICIPATING",
120
  "202": "NON_PARTICIPATING",
 
123
  "205": "NON_PARTICIPATING",
124
  "206": "NON_PARTICIPATING",
125
  "207": "NON_PARTICIPATING",
126
+ "208": "NON_PARTICIPATING",
127
  "209": "NON_PARTICIPATING",
128
  "21": "SUCCESS",
129
  "210": "NON_PARTICIPATING",
130
+ "211": "NON_PARTICIPATING",
131
  "212": "SUCCESS",
132
  "213": "NON_PARTICIPATING",
133
  "214": "NON_PARTICIPATING",
 
136
  "217": "NON_PARTICIPATING",
137
  "218": "NON_PARTICIPATING",
138
  "219": "NON_PARTICIPATING",
139
+ "22": "NON_PARTICIPATING",
140
  "220": "NON_PARTICIPATING",
141
  "221": "NON_PARTICIPATING",
142
  "222": "NON_PARTICIPATING",
143
  "223": "NON_PARTICIPATING",
144
  "224": "NON_PARTICIPATING",
145
  "225": "NON_PARTICIPATING",
146
+ "226": "NON_PARTICIPATING",
147
  "227": "NON_PARTICIPATING",
148
  "228": "NON_PARTICIPATING",
149
  "229": "NON_PARTICIPATING",
150
+ "23": "NON_PARTICIPATING",
151
  "230": "NON_PARTICIPATING",
152
  "231": "NON_PARTICIPATING",
153
  "232": "NON_PARTICIPATING",
154
  "233": "NON_PARTICIPATING",
155
+ "234": "SUCCESS",
156
  "235": "NON_PARTICIPATING",
157
  "236": "NON_PARTICIPATING",
158
  "237": "NON_PARTICIPATING",
 
179
  "26": "NON_PARTICIPATING",
180
  "27": "NON_PARTICIPATING",
181
  "28": "NON_PARTICIPATING",
182
+ "29": "NON_PARTICIPATING",
183
+ "3": "SUCCESS",
184
+ "30": "NON_PARTICIPATING",
185
  "31": "NON_PARTICIPATING",
186
  "32": "NON_PARTICIPATING",
187
  "33": "NON_PARTICIPATING",
188
  "34": "SUCCESS",
189
+ "35": "NON_PARTICIPATING",
190
  "36": "NON_PARTICIPATING",
191
  "37": "SUCCESS",
192
+ "38": "NON_PARTICIPATING",
193
+ "39": "NON_PARTICIPATING",
194
  "4": "SUCCESS",
195
+ "40": "NON_PARTICIPATING",
196
+ "41": "NON_PARTICIPATING",
197
+ "42": "NON_PARTICIPATING",
198
  "43": "NON_PARTICIPATING",
199
+ "44": "NON_PARTICIPATING",
200
  "45": "SUCCESS",
201
  "46": "SUCCESS",
202
  "47": "NON_PARTICIPATING",
203
  "48": "NON_PARTICIPATING",
204
+ "49": "NON_PARTICIPATING",
205
+ "5": "SUCCESS",
206
+ "50": "SUCCESS",
207
+ "51": "SUCCESS",
208
  "52": "NON_PARTICIPATING",
209
  "53": "NON_PARTICIPATING",
210
+ "54": "NON_PARTICIPATING",
211
+ "55": "SUCCESS",
212
+ "56": "NON_PARTICIPATING",
213
+ "57": "NON_PARTICIPATING",
214
  "58": "NON_PARTICIPATING",
215
  "59": "NON_PARTICIPATING",
216
+ "6": "SUCCESS",
217
+ "60": "SUCCESS",
218
+ "61": "SUCCESS",
219
  "62": "NON_PARTICIPATING",
220
  "63": "SUCCESS",
221
  "64": "SUCCESS",
222
  "65": "SUCCESS",
223
+ "66": "SUCCESS",
224
  "67": "SUCCESS",
225
+ "68": "NON_PARTICIPATING",
226
  "69": "NON_PARTICIPATING",
227
  "7": "NON_PARTICIPATING",
228
  "70": "SUCCESS",
229
+ "71": "NON_PARTICIPATING",
230
+ "72": "NON_PARTICIPATING",
231
  "73": "NON_PARTICIPATING",
232
+ "74": "SUCCESS",
233
+ "75": "SUCCESS",
234
  "76": "NON_PARTICIPATING",
235
+ "77": "NON_PARTICIPATING",
236
  "78": "SUCCESS",
237
  "79": "SUCCESS",
238
+ "8": "SUCCESS",
239
  "80": "SUCCESS",
240
  "81": "NON_PARTICIPATING",
241
+ "82": "NON_PARTICIPATING",
242
  "83": "NON_PARTICIPATING",
243
  "84": "SUCCESS",
244
  "85": "SUCCESS",
245
+ "86": "SUCCESS",
246
  "87": "NON_PARTICIPATING",
247
  "88": "NON_PARTICIPATING",
248
  "89": "NON_PARTICIPATING",
249
  "9": "NON_PARTICIPATING",
250
  "90": "NON_PARTICIPATING",
251
+ "91": "NON_PARTICIPATING",
252
  "92": "NON_PARTICIPATING",
253
+ "93": "SUCCESS",
254
  "94": "NON_PARTICIPATING",
255
+ "95": "NON_PARTICIPATING",
256
  "96": "NON_PARTICIPATING",
257
+ "97": "NON_PARTICIPATING",
258
+ "98": "SUCCESS",
259
+ "99": "NON_PARTICIPATING"
260
  },
261
  "architectures": [
262
  "LlamaForCausalLM"
 
264
  "attention_bias": false,
265
  "attention_dropout": 0.0,
266
  "block_list": [
267
+ 5716493,
268
+ 5716509
269
  ],
270
  "bos_token_id": 1,
271
  "eos_token_id": 2,
272
  "hidden_act": "silu",
273
  "hidden_size": 2048,
274
  "initializer_range": 0.02,
275
+ "inner_step": 1,
276
  "intermediate_size": 5632,
277
+ "last_allreduce_block": 5716303,
278
  "max_position_embeddings": 2048,
279
  "mlp_bias": false,
280
  "model_type": "llama",
inner_optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e341eaa58f58e497ad2c83572c4a72a532b3e792e3f320b6770e6b4ffcbe8435
3
  size 8800564076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0660f300f662a9c6f2a13573f7b02ca36b19dda22357770ce3fff2489ff4480
3
  size 8800564076
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23ebd3c89dda8dfac4bf4583a132ac443ac5e8b856632b7930b4b3391e283a20
3
  size 4400216536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089af4dee9bc224abb604ff154c71de2345f1cec8f0dd8dc281e1f5a15507417
3
  size 4400216536